© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84115
    Prev
    Next
    INDEX
    Explanations

    reported

    np_acts-logits-general · gemini-2.5-flash-lite

    CRISPR, ternary, month, comment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zień
    0.47
    ettle
    0.47
    ung
    0.46
    ږئ
    0.46
    hesh
    0.44
    ederal
    0.44
     zamknię
    0.44
    __,
    0.43
    ering
    0.43
    дагы
    0.43
    POSITIVE LOGITS
    פ
    0.47
    슘
    0.46
    ี
    0.46
    聲
    0.46
    빌
    0.46
    協
    0.45
    嬰
    0.45
    ऑ
    0.45
    監
    0.45
    譴
    0.45
    Activations Density 0.000%

    No Known Activations